{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 1605, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 14.7899808883667, "learning_rate": 1.3333333333333333e-05, "loss": 0.4866, "step": 535 }, { "epoch": 1.0, "eval_loss": 0.42115479707717896, "eval_matthews_correlation": 0.5497032501894998, "eval_runtime": 4.7251, "eval_samples_per_second": 220.738, "eval_steps_per_second": 27.724, "step": 535 }, { "epoch": 2.0, "grad_norm": 33.17850112915039, "learning_rate": 6.666666666666667e-06, "loss": 0.2848, "step": 1070 }, { "epoch": 2.0, "eval_loss": 0.5097023844718933, "eval_matthews_correlation": 0.5726999708077573, "eval_runtime": 4.4553, "eval_samples_per_second": 234.104, "eval_steps_per_second": 29.403, "step": 1070 }, { "epoch": 3.0, "grad_norm": 0.3264881372451782, "learning_rate": 0.0, "loss": 0.1867, "step": 1605 }, { "epoch": 3.0, "eval_loss": 0.6564142107963562, "eval_matthews_correlation": 0.5577353353156735, "eval_runtime": 4.4818, "eval_samples_per_second": 232.721, "eval_steps_per_second": 29.23, "step": 1605 }, { "epoch": 3.0, "step": 1605, "total_flos": 6749587903150080.0, "train_loss": 0.31938580189167154, "train_runtime": 346.8226, "train_samples_per_second": 73.966, "train_steps_per_second": 4.628 } ], "logging_steps": 500, "max_steps": 1605, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6749587903150080.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }